Unmanned Surface Vessel Cluster Path Planning Based on Deep Reinforcement Learning
With the wide application of unmanned surface vessels(USVs) in the field of maritime search, the traditional path planning algorithms fail to meet the complex rescue scenarios, which can lead to local optimum, low task completion rate, and slow convergence speed. For this reason, a path planning met...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Science Press (China)
2025-04-01
|
| Series: | 水下无人系统学报 |
| Subjects: | |
| Online Access: | https://sxwrxtxb.xml-journal.net/cn/article/doi/10.11993/j.issn.2096-3920.2024-0179 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849426949333581824 |
|---|---|
| author | Manjiang YU Jiawei HE Bowen XING |
| author_facet | Manjiang YU Jiawei HE Bowen XING |
| author_sort | Manjiang YU |
| collection | DOAJ |
| description | With the wide application of unmanned surface vessels(USVs) in the field of maritime search, the traditional path planning algorithms fail to meet the complex rescue scenarios, which can lead to local optimum, low task completion rate, and slow convergence speed. For this reason, a path planning method for USV cluster cooperative search and rescue was proposed. Firstly, a long and short-term memory module was introduced based on the multi-agent deep deterministic policy gradient algorithm to enhance the ability of the USVs to utilize the temporal information in path planning; secondly, a multi-level representational experience pool was designed to improve the training efficiency and data utilization and reduce the interference between different experiences; finally, stochastic network distillation was used as a curiosity mechanism to provide intrinsic rewards for the USVs to explore new regions and solve the convergence due to the sparse rewards. The simulation experiment results show that the improved algorithm improves the convergence speed by about 38.46% compared with the original algorithm, and the path length has been shortened by 27.02%. In addition, the obstacle avoidance ability has been significantly improved. |
| format | Article |
| id | doaj-art-c35e26e66fb34b37b96a90a63d97ac62 |
| institution | Kabale University |
| issn | 2096-3920 |
| language | zho |
| publishDate | 2025-04-01 |
| publisher | Science Press (China) |
| record_format | Article |
| series | 水下无人系统学报 |
| spelling | doaj-art-c35e26e66fb34b37b96a90a63d97ac622025-08-20T03:29:10ZzhoScience Press (China)水下无人系统学报2096-39202025-04-0133238038810.11993/j.issn.2096-3920.2024-01792024-0179Unmanned Surface Vessel Cluster Path Planning Based on Deep Reinforcement LearningManjiang YU0Jiawei HE1Bowen XING2College of Engineering, Shanghai Ocean University, Shanghai 201306, ChinaMarine Design and Research Institute of China, Shanghai 200011, ChinaCollege of Engineering, Shanghai Ocean University, Shanghai 201306, ChinaWith the wide application of unmanned surface vessels(USVs) in the field of maritime search, the traditional path planning algorithms fail to meet the complex rescue scenarios, which can lead to local optimum, low task completion rate, and slow convergence speed. For this reason, a path planning method for USV cluster cooperative search and rescue was proposed. Firstly, a long and short-term memory module was introduced based on the multi-agent deep deterministic policy gradient algorithm to enhance the ability of the USVs to utilize the temporal information in path planning; secondly, a multi-level representational experience pool was designed to improve the training efficiency and data utilization and reduce the interference between different experiences; finally, stochastic network distillation was used as a curiosity mechanism to provide intrinsic rewards for the USVs to explore new regions and solve the convergence due to the sparse rewards. The simulation experiment results show that the improved algorithm improves the convergence speed by about 38.46% compared with the original algorithm, and the path length has been shortened by 27.02%. In addition, the obstacle avoidance ability has been significantly improved.https://sxwrxtxb.xml-journal.net/cn/article/doi/10.11993/j.issn.2096-3920.2024-0179unmanned surface vesseldeep reinforcement learninglong and short-term memorycuriosity mechanismpath planning |
| spellingShingle | Manjiang YU Jiawei HE Bowen XING Unmanned Surface Vessel Cluster Path Planning Based on Deep Reinforcement Learning 水下无人系统学报 unmanned surface vessel deep reinforcement learning long and short-term memory curiosity mechanism path planning |
| title | Unmanned Surface Vessel Cluster Path Planning Based on Deep Reinforcement Learning |
| title_full | Unmanned Surface Vessel Cluster Path Planning Based on Deep Reinforcement Learning |
| title_fullStr | Unmanned Surface Vessel Cluster Path Planning Based on Deep Reinforcement Learning |
| title_full_unstemmed | Unmanned Surface Vessel Cluster Path Planning Based on Deep Reinforcement Learning |
| title_short | Unmanned Surface Vessel Cluster Path Planning Based on Deep Reinforcement Learning |
| title_sort | unmanned surface vessel cluster path planning based on deep reinforcement learning |
| topic | unmanned surface vessel deep reinforcement learning long and short-term memory curiosity mechanism path planning |
| url | https://sxwrxtxb.xml-journal.net/cn/article/doi/10.11993/j.issn.2096-3920.2024-0179 |
| work_keys_str_mv | AT manjiangyu unmannedsurfacevesselclusterpathplanningbasedondeepreinforcementlearning AT jiaweihe unmannedsurfacevesselclusterpathplanningbasedondeepreinforcementlearning AT bowenxing unmannedsurfacevesselclusterpathplanningbasedondeepreinforcementlearning |